CN117893121B - System and method for monitoring article transportation state by utilizing artificial intelligence - Google Patents
System and method for monitoring article transportation state by utilizing artificial intelligence Download PDFInfo
- Publication number
- CN117893121B CN117893121B CN202410297060.8A CN202410297060A CN117893121B CN 117893121 B CN117893121 B CN 117893121B CN 202410297060 A CN202410297060 A CN 202410297060A CN 117893121 B CN117893121 B CN 117893121B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- transportation
- article
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0833—Tracking
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明涉及物流运输技术领域，公开了一种利用人工智能监测物品运输状态系统及方法。本发明通过在需要监测运输状态的运输物品周围安装相应的监控终端设备，并通过监控终端设备中的各个监测模块对运输物品进行实时监测；同时，监控终端设备会基于无线通信方式实时上传控终端设备中的各个监测模块监测到的数据，并交由监控平台对各个监测模块监测到的数据进行分析，通过D‑S证据理论合理的分析该运输物品的实时状态；进而基于分析的实时状态判断是否要对该物品运输过程进行调整，提高了监测物品运输状态的合理性和实时性。
The present invention relates to the field of logistics and transportation technology, and discloses a system and method for monitoring the transportation status of items using artificial intelligence. The present invention installs corresponding monitoring terminal devices around the transported items whose transportation status needs to be monitored, and monitors the transported items in real time through various monitoring modules in the monitoring terminal devices; at the same time, the monitoring terminal devices will upload the data monitored by various monitoring modules in the terminal devices in real time based on wireless communication, and the monitoring platform will analyze the data monitored by various monitoring modules, and reasonably analyze the real-time status of the transported items through the D-S evidence theory; and then judge whether to adjust the transportation process of the items based on the analyzed real-time status, thereby improving the rationality and real-time nature of monitoring the transportation status of items.
Description
Technical Field
The invention relates to the technical field of logistics transportation (G06Q 10/08), in particular to a system and a method for monitoring article transportation state by utilizing artificial intelligence.
Background
With the rising and development of modern logistics transportation industry, other related industries also develop vigorously. During logistic transport, transport accidents may occur due to human factors or other unpredictable accidents. In logistics transportation, the transportation safety of dangerous chemicals is important, and once dangerous chemical transportation accidents occur, explosion, leakage, combustion and other conditions are often caused, so that serious consequences can be caused to the environment, personnel, life and property safety. In the transportation of related products of electromechanical equipment, the transported equipment usually contains materials such as metal, electronic components and the like, has the characteristics of long research and development period, high technical content and precision degree, complex structure and difficult estimation of cost, and after the equipment is produced, the equipment needs to be transported to a use place through logistics transportation, and the equipment receives acceleration, temperature and humidity, electromagnetic interference and other environmental factors, so that the safety quality of the equipment transportation can be influenced.
Therefore, in the process of transporting goods, the transportation environment and state of the transported goods are critical to the transportation safety of the goods. Therefore, the method and the device can timely and accurately know the transportation state of the goods, monitor the transportation environment parameters of the transportation process, acquire the transportation process information of the goods, and have important economic and application values for ensuring the transportation safety of the goods and improving the reliability and quality monitoring level of logistics transportation.
Disclosure of Invention
(One) solving the technical problems
Aiming at the defects of the prior art, the invention provides a system and a method for monitoring the article transportation state by utilizing artificial intelligence, which have the advantages of real-time performance, safety and the like and solve the problem of influence on the transportation process due to external factors.
(II) technical scheme
In order to solve the technical problem that the external factors influence the transportation process, the invention provides the following technical scheme:
S1, installing monitoring terminal equipment for each article in the article transportation process, and communicating with a monitoring platform in real time in a wireless communication mode;
s2, the installed monitoring terminal equipment collects information of transported objects based on the configuration of the internet of things sensor;
s3, monitoring the state of the transported object in real time according to the information data of the transported object collected in real time, and carrying out periodic reporting; the abnormal condition is judged based on a state vector algorithm, and specifically comprises the following steps:
s31, constructing an information data vector; the information data at least comprises position data, state data, vibration data and transport tool data of the transported articles; constructing information data vectors from the information data The method meets the following conditions:
Wherein a i1 to a in represent position data elements of the i-th transport item; b i1 to b im represent status data elements of the ith transport item; c i1 to c if represent vibration data elements of the ith transport item; d i1 to d ig denote transport data elements of the ith transport item, [ I ] denotes a transport item number space, [ J ] denotes an information data number space;
s32, classifying areas of the transported objects; from information data vectors In calling position data element, constructing position data vectorThe method meets the following conditions:
position data vector for all transported items Clustering analysis is carried out, and the articles with the same type of analysis result are divided into articles in areas;
S33, judging the sports goods; the method specifically comprises the following steps:
S331, data vector for regional object Performing time derivation to obtain a time-varying vector/>, of the position data
S332, judging time-varying vector of position dataWhether the article is smaller than a preset first threshold value or not, if yes, judging that the article is a static article, and if not, judging that the article is an article in transportation;
S333, for the article in transport, time-varying vector of the position data thereof Performing cluster analysis, and judging the articles with the same analysis structure as articles with the same carrier;
s34, judging the transportation state; for co-carrier articles, from information data vectors In the process, the vibration data elements are called, and the vibration data vector/> isconstructedFor vibration data vectorPerforming cluster analysis to find out an outlier vibration data vector, and judging that the transported object is an abnormal vibration object;
S35, judging the state of the abnormal vibration article; the method comprises the steps of calling state data b i1,bi2,…,bim of an abnormal vibration article, constructing transportation state data { b i1,bi2,…,bim }, comparing the transportation state data with an expected state data interval set { [ b i1],[bi2],…,[bim ] } element by element, judging whether abnormal elements exist, judging that current transportation tool data are not abnormal if the abnormal elements exist, and judging that the current transportation tool data are abnormal if the abnormal transportation tool data are not abnormal;
When an abnormal condition occurs, the monitoring terminal equipment alarms and reports the abnormal state of the transported articles;
s4, uploading the state of the transported object monitored in real time to a monitoring platform, processing the state based on the uploaded monitoring data by the monitoring platform, and generating an instruction based on user requirements by the monitoring platform to control the monitoring terminal equipment;
S5, the monitoring platform transmits the processed data to the user side through the server and interacts with the user through the user side;
preferably, the communicating with the monitoring platform in real time by means of wireless communication includes the following steps:
S11, creating an interface at a monitoring terminal device end and a monitoring platform end;
S12, binding the IP address and the interface;
s13, realizing communication between the two interfaces through the appointed IP address.
Preferably, the collecting, by the installed monitoring terminal device, information of the transported articles based on the configuration of the internet of things sensor includes: and (3) environmental data acquisition: data information acquisition is carried out on the temperature and humidity environment around the monitoring terminal;
And (3) geographic positioning data acquisition: carrying out coordinate positioning on geographic position information in the logistics transportation process to determine the position information of the article;
And (3) image shooting and acquisition: and after receiving a shooting instruction from the monitoring platform, collecting shooting image information of the state of the article in the logistics transportation process.
Preferably, the monitoring the status of the transported object in real time according to the information data of the transported object collected in real time further comprises the following steps:
s36, rechecking the article transportation state; the method specifically comprises the following steps:
S361, setting a D-S evidence theory;
s362, setting a D-S combination rule;
S363, calculating key parameter weights;
s364, setting corresponding thresholds according to the weights of the indexes and judging the article transportation state based on the D-S evidence theory.
Preferably, the set D-S evidence theory:
Defining a basic probability distribution function:
Setting a quality function mapping m, namely 2 θ to 0, 1;
and m satisfies:
Then m is a probability distribution function of 2 θ;
Wherein, Is an empty set, m (A) is the confidence of A itself, θ is a certain finite set, 2 θ represents a set made up of all subsets of the expert ranking opinion table, A represents a set of assumptions in θ;
further, defining a confidence function Bel and a likelihood function Pl based on the probability distribution function;
Setting a mapping Bel 2 θ to 0, 1;
when meeting the requirements Bel(θ)＝1；
And for any subset a 1,A2,...,An of θ:
And has the following steps:
the map Pl.2 θ. Fwdarw.0, 1 is a belief function defined at θ;
wherein I represents the number of elements in set I;
setting a mapping Pl of 2 θ to 0, 1;
when meeting the requirements Pl(θ)＝1；
And for any subset a 1,A2,...,An of θ:
the map Pl.2 θ. Fwdarw.0, 1 is a belief function defined at θ;
Where I represents the number of elements in set I.
Preferably, the setting D-S combination rule:
Setting m 1,m2 to be the quality function defined on θ, respectively, then:
Wherein E, F are respectively the hypothesis sets in θ, A is not the null set; Is a normalization constant;
Setting m as a mass function synthesized by m 1,m2:
m＝m1⊕m2
Setting a synthesis formula:
Wherein E i represents the i-th number in set E.
Preferably, the calculating key parameter weights:
setting n indexes u j (j=1, 2,..n), and inviting k experts to rank the indexes;
The expert ranks the indexes according to the difference of the importance degrees of the indexes, wherein the most important index is 1, the least important index is n, and the same serial number can be ranked if the expert considers that a plurality of indexes are equally important;
Recording the sequence of each index, and constructing a sequence opinion table;
acquiring all indexes collected by monitoring terminal equipment in the transportation process in real time, and calculating the weight of all indexes in an expert sorting opinion table based on the difference of transported articles and the expert sorting opinion table corresponding to different transported articles;
The collection index set u= { U 1,u2,...,un }, the rank array given by the ith expert is { a i1,ai2,...,ain }, and the membership functions of the rank transformation are determined for a typical rank as follows:
X(M)＝-p(M)lnp(M),M＝1,2,...,n
Wherein the method comprises the steps of
Let m=a ij, b ij＝X(aij),bij be the membership function value corresponding to the ranking number M; taking an average value of the array { b 1j,...,bkj }, marking as b j, and weighing 1-b j as the average recognition degree of k experts on the index u j;
The membership function value of k experts on the cognition of the index u is recorded as Q, and is defined as:
Qj＝max{b1j,b2j,...,bkj}
Setting the overall recognition degree of k experts on the index u j as x j;
xj＝(1-bj)(1-Qj)
and carrying out normalization treatment:
The weight vector α j for each index can be obtained.
Preferably, the weight of each index is set to a corresponding threshold value, and the article transportation state is judged based on the D-S evidence theory: setting the maximum boundary value of three key parameters with the maximum weight in the index as a system threshold, namely when any one of the three key parameters is acquired to reach a dangerous state range, waking up a monitoring system to start storing effective key data, and after the data within N seconds are acquired and stored, performing multi-data fusion processing on the acquired effective key parameters;
Performing basic trust distribution on N groups of effective key parameters acquired in N seconds through a set threshold value;
Normalization processing is carried out on the collected effective key parameters, and a basic trust distribution set theta= { safe, safer, more dangerous and dangerous } is set and identified, and a fused input matrix R is obtained according to D-S evidence:
based on the weights of the various indices, new evidence for each data is calculated:
Obtaining a final fusion result vector based on a synthesis formula:
Wherein a 1+A2+A3+A4 =1, when a 1 is the maximum value of four components in the fusion result vector, the transportation state is safe; when A 2 is the maximum value of the four components in the fusion result vector, the transportation state is safer; when A 3 is the maximum value of the four components in the fusion result vector, the transportation state is dangerous, and the image shooting module is started to monitor the transportation state of the article in real time and remind transportation personnel to slow down the speed of the vehicle; when A 4 is the maximum value of the four components in the fusion result vector, the transportation state is dangerous, and an alarm signal is generated at the moment to remind transportation personnel to stop and check immediately;
Further, the user can send shooting instructions to the monitoring terminal equipment through the monitoring platform to check the state of the current article in real time;
The user can send shooting instructions to the monitoring terminal equipment through the monitoring platform to check the state of the current article in real time, and the method comprises the following steps of:
S51, after receiving a shooting instruction input by a user in a management portal, the monitoring platform transmits the shooting instruction to the monitoring terminal equipment based on wireless communication with the monitoring terminal equipment;
s52, after receiving a shooting instruction from the monitoring platform, the monitoring terminal equipment generates a corresponding starting signal to activate an image shooting module in the monitoring terminal equipment;
s53, the image shooting module monitors the state of the transported object in real time after receiving a starting signal from the monitoring terminal equipment;
S54, after the image shooting module is started, the monitoring terminal equipment adjusts the communication protocol of the wireless communication module, and establishes reliable communication connection with a management portal in the monitoring platform through the newly adjusted communication protocol, so that stable transmission of the transported object images is ensured;
And S55, when the user closes the management portal or cancels the shooting instruction, the monitoring platform transmits the canceling instruction in real time, and meanwhile, the monitoring terminal equipment generates a closing signal after receiving the canceling instruction, closes the image shooting module and adjusts the communication protocol of the wireless communication module.
The embodiment also discloses a system for monitoring the article transportation state by using artificial intelligence, which specifically comprises: monitoring terminal equipment and a monitoring platform;
The monitoring terminal device includes: the system comprises a humidity monitoring module, a temperature monitoring module, an image shooting module, an article transportation state collecting module, an alarm module, a wireless communication module and a GPS positioning module;
the humidity monitoring module is used for monitoring the humidity of the surrounding environment of the transported article in real time;
the temperature monitoring module is used for monitoring the temperature of the surrounding environment of the transported article in real time;
the image shooting module is used for shooting images of the transported objects in real time according to the instruction;
The article transportation state collection module is used for collecting state parameters in the article transportation process in real time;
the alarm module is used for receiving the state signal in the article transportation process in real time and carrying out alarm processing on the dangerous state signal in the article transportation process;
The wireless communication module is used for carrying out wireless communication with the monitoring platform and carrying out data transmission with the monitoring platform;
the GPS positioning module is used for updating positioning information in the process of transporting the articles in real time according to the GPS positioning signals;
The monitoring platform comprises: a data analysis module, a management portal;
The data analysis module is used for analyzing data from the monitoring terminal equipment and judging the current article transportation state in real time;
the management portal is used for displaying the article transportation state in real time and interacting with a user.
(III) beneficial effects
Compared with the prior art, the invention provides a system and a method for monitoring the article transportation state by utilizing artificial intelligence, which have the following beneficial effects:
1. according to the method, the classification of multi-source information fusion is introduced through a D-S evidence theory, the influence weights of all the motion parameters are reasonably calculated according to the difference of the motion parameters on the transportation safety influence degree of the articles, and finally the transportation state of the articles is calculated according to the set parameter index threshold and all the index parameters monitored by the monitoring terminal equipment in real time and evaluated, so that the real-time transportation state result of the article transportation process is more comprehensive, comprehensive and accurate.
2. According to the invention, by installing the terminal monitoring equipment around the article in the transportation state to be monitored, various environmental parameters generated in the transportation process of the article are collected in real time, and the collected various environmental parameters are transmitted to the monitoring platform in real time and transmitted to the monitoring platform to analyze various environmental parameters generated in the transportation process in real time, so that whether the transported article has a dangerous transportation state or not is judged, and the safety of the transportation of the article is improved.
3. According to the invention, the environment parameter change condition in the article transportation process is monitored in real time, the article transportation state is analyzed based on the environment parameter change condition, and when the article transportation state is judged to be dangerous, alarm information is immediately generated to remind transportation personnel to detect, so that the real-time performance and reliability of safe transportation of the articles are improved.
4. The invention realizes the opening and closing of the image shooting module in the monitoring terminal device by the way of inputting shooting instructions by a user, realizes the monitoring of the state of the transported object by the way of shooting the image shooting module in the monitoring terminal device in real time, and ensures the stability and reliability of the image data transmission of the transported object by the way of adjusting the communication protocol of the wireless communication module in real time by the monitoring terminal device.
Drawings
FIG. 1 is a schematic diagram of the process flow of the process of transporting the monitored articles according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment discloses a method for monitoring article transportation state by utilizing artificial intelligence, which specifically comprises the following steps:
S1, installing monitoring terminal equipment for each article in the article transportation process, and communicating with a monitoring platform in real time in a wireless communication mode;
s2, the installed monitoring terminal equipment collects information of transported objects based on the configuration of the internet of things sensor;
s3, monitoring the state of the transported object in real time according to the information data of the transported object collected in real time, and carrying out periodic reporting; the abnormal condition is judged based on a state vector algorithm, and specifically comprises the following steps:
s31, constructing an information data vector; the information data at least comprises position data, state data, vibration data and transport tool data of the transported articles; constructing information data vectors from the information data The method meets the following conditions:
Wherein a i1 to a in represent position data elements of the i-th transport item; b i1 to b im represent status data elements of the ith transport item; c i1 to c if represent vibration data elements of the ith transport item; d i1 to d ig denote transport data elements of the ith transport item, [ I ] denotes a transport item number space, [ J ] denotes an information data number space;
s32, classifying areas of the transported objects; from information data vectors In calling position data element, constructing position data vectorThe method meets the following conditions:
position data vector for all transported items Clustering analysis is carried out, and the articles with the same type of analysis result are divided into articles in areas;
S33, judging the sports goods; the method specifically comprises the following steps:
S331, data vector for regional object Performing time derivation to obtain a time-varying vector/>, of the position data
S332, judging time-varying vector of position dataWhether the article is smaller than a preset first threshold value or not, if yes, judging that the article is a static article, and if not, judging that the article is an article in transportation;
S333, for the article in transport, time-varying vector of the position data thereof Performing cluster analysis, and judging the articles with the same analysis structure as articles with the same carrier;
s34, judging the transportation state; for co-carrier articles, from information data vectors In the process, the vibration data elements are called, and the vibration data vector/> isconstructedFor vibration data vectorPerforming cluster analysis to find out an outlier vibration data vector, and judging that the transported object is an abnormal vibration object;
S35, judging the state of the abnormal vibration article; the method comprises the steps of calling state data b i1,bi2,…,bim of an abnormal vibration article, constructing transportation state data { b i1,bi2,…,bim }, comparing the transportation state data with an expected state data interval set { [ b i1],[bi2],…,[bim ] } element by element, judging whether abnormal elements exist, judging that current transportation tool data are not abnormal if the abnormal elements exist, and judging that the current transportation tool data are abnormal if the abnormal transportation tool data are not abnormal;
When an abnormal condition occurs, the monitoring terminal equipment alarms and reports the abnormal state of the transported articles;
s4, uploading the state of the transported object monitored in real time to a monitoring platform, processing the state based on the uploaded monitoring data by the monitoring platform, and generating an instruction based on user requirements by the monitoring platform to control the monitoring terminal equipment;
S5, the monitoring platform transmits the processed data to the user side through the server and interacts with the user through the user side;
further, the communicating with the monitoring platform in real time by means of wireless communication includes:
S11, creating an interface at a monitoring terminal device end and a monitoring platform end;
S12, binding the IP address and the interface;
S13, realizing communication between two interfaces through the appointed IP address;
Further, the installed monitoring terminal device can collect information of the transported objects based on the configuration of the internet of things sensor, including:
and (3) environmental data acquisition: data information acquisition is carried out on the temperature and humidity environment around the monitoring terminal;
And (3) geographic positioning data acquisition: carrying out coordinate positioning on geographic position information in the logistics transportation process to determine the position information of the article;
And (3) image shooting and acquisition: after receiving a shooting instruction from the monitoring platform, collecting shooting image information of the state of the article in the logistics transportation process;
Further, the real-time monitoring of the state of the transported object according to the information data of the transported object collected in real time comprises the following steps:
S361, setting a D-S evidence theory;
Defining a basic probability distribution function:
Setting a quality function mapping m, namely 2 θ to 0, 1;
And the mass function m satisfies: When in use;
Then m is a probability distribution function of 2 θ;
Wherein, Is an empty set, m (A) is the confidence of A itself, θ is a certain finite set, 2 θ represents a set made up of all subsets of the expert ranking opinion table, A represents a set of assumptions in θ;
further, defining a confidence function Bel and a likelihood function Pl based on the probability distribution function;
Setting a mapping Bel 2 θ to 0, 1;
when meeting the requirements Bel(θ)＝1；
And for any subset a 1,A2,...,An of θ:
And has the following steps: When in use;
the map Pl.2 θ. Fwdarw.0, 1 is a belief function defined at θ;
wherein I represents the number of elements in set I;
setting a mapping Pl of 2 θ to 0, 1;
when meeting the requirements Pl(θ)＝1；
And for any subset a 1,A2,...,An of θ:
the map Pl.2 θ. Fwdarw.0, 1 is a belief function defined at θ;
wherein I represents the number of elements in set I;
s362, setting a D-S combination rule;
Setting m 1,m2 to be the quality function defined on θ, respectively, then:
Wherein E, F are respectively the hypothesis sets in θ, A is not the null set; Is a normalization constant;
Setting m as a mass function synthesized by m 1,m2:
m＝m1⊕m2
Setting a synthesis formula:
Wherein E i represents the ith number in set E;
S363, calculating key parameter weights;
setting n indexes u j (j=1, 2,..n), and inviting k experts to rank the indexes;
The expert ranks the indexes according to the difference of the importance degrees of the indexes, wherein the most important index is 1, the least important index is n, and the same serial number can be ranked if the expert considers that a plurality of indexes are equally important;
Recording the sequence of each index, and constructing a sequence opinion table;
Further, acquiring all indexes collected by the monitoring terminal equipment in the transportation process in real time, and calculating the weight of all indexes in the expert sorting opinion table based on the difference of transported articles and the expert sorting opinion table corresponding to different transported articles;
The collection index set u= { U 1,u2,...,un }, the rank array given by the ith expert is { a i1,ai2,...,ain }, and the membership functions of the rank transformation are determined for a typical rank as follows:
X(M)＝-p(M)lnp(M),M＝1,2,...,n
Wherein the method comprises the steps of
Let m=a ij, b ij＝X(aij),bij be the membership function value corresponding to the ranking number M; taking an average value of the array { b 1j,...,bkj }, marking as b j, and weighing 1-b j as the average recognition degree of k experts on the index u j;
The membership function value of k experts on the cognition of the index u is recorded as Q, and is defined as:
Qj＝max{b1j,b2j,...,bkj}
Setting the overall recognition degree of k experts on the index u j as x j;
xj＝(1-bj)(1-Qj)
and carrying out normalization treatment:
the weight vector alpha j of each index can be obtained;
S364, setting corresponding thresholds according to the weights of the indexes and judging the article transportation state based on the D-S evidence theory;
Further, setting the maximum boundary value of three key parameters with the maximum weight in the index as a system threshold, namely when any one of the three key parameters is acquired to reach a dangerous state range, waking up a monitoring system to start storing effective key data, and after the data within N seconds are acquired and stored, performing multi-data fusion processing on the acquired effective key parameters;
Further, performing basic trust distribution on N groups of effective key parameters acquired in N seconds through a set threshold value;
Further, normalization processing is carried out on the collected effective key parameters, and the identification basic trust distribution set theta= { safe, safer, more dangerous and dangerous }, and a fused input matrix R is obtained according to D-S evidence:
further, new evidence for each data is calculated based on the weights of the respective indicators:
Further, a final fusion result vector is obtained based on the synthesis formula:
Wherein a 1+A2+A3+A4 =1, when a 1 is the maximum value of four components in the fusion result vector, the transportation state is safe; when A 2 is the maximum value of the four components in the fusion result vector, the transportation state is safer; when A 3 is the maximum value of the four components in the fusion result vector, the transportation state is dangerous, and the image shooting module is started to monitor the transportation state of the article in real time and remind transportation personnel to slow down the speed of the vehicle; when A 4 is the maximum value of the four components in the fusion result vector, the transportation state is dangerous, and an alarm signal is generated at the moment to remind transportation personnel to stop and check immediately;
safety, safer, more dangerous and dangerous are sequentially from high to low according to the safety.
Further, the user can send shooting instructions to the monitoring terminal equipment through the monitoring platform to check the state of the current article in real time;
The user can send shooting instructions to the monitoring terminal equipment through the monitoring platform to check the state of the current article in real time, and the method comprises the following steps of:
S51, after receiving a shooting instruction input by a user in a management portal, the monitoring platform transmits the shooting instruction to the monitoring terminal equipment based on wireless communication with the monitoring terminal equipment;
s52, after receiving a shooting instruction from the monitoring platform, the monitoring terminal equipment generates a corresponding starting signal to activate an image shooting module in the monitoring terminal equipment;
s53, the image shooting module monitors the state of the transported object in real time after receiving a starting signal from the monitoring terminal equipment;
S54, after the image shooting module is started, the monitoring terminal equipment adjusts the communication protocol of the wireless communication module, and establishes reliable communication connection with a management portal in the monitoring platform through the newly adjusted communication protocol, so that stable transmission of the transported object images is ensured;
S55, when a user closes a management portal or cancels a shooting instruction, the monitoring platform transmits the canceling instruction in real time, and meanwhile, the monitoring terminal equipment generates a closing signal after receiving the canceling instruction, closes an image shooting module and adjusts a communication protocol of the wireless communication module;
the embodiment also discloses a system for monitoring the article transportation state by using artificial intelligence, which specifically comprises: monitoring terminal equipment and a monitoring platform;
The monitoring terminal device includes: the system comprises a humidity monitoring module, a temperature monitoring module, an image shooting module, an article transportation state collecting module, an alarm module, a wireless communication module and a GPS positioning module;
the humidity monitoring module is used for monitoring the humidity of the surrounding environment of the transported article in real time;
the temperature monitoring module is used for monitoring the temperature of the surrounding environment of the transported article in real time;
the image shooting module is used for shooting images of the transported objects in real time according to the instruction;
The article transportation state collection module is used for collecting state parameters in the article transportation process in real time;
the alarm module is used for receiving the state signal in the article transportation process in real time and carrying out alarm processing on the dangerous state signal in the article transportation process;
The wireless communication module is used for carrying out wireless communication with the monitoring platform and carrying out data transmission with the monitoring platform;
the GPS positioning module is used for updating positioning information in the process of transporting the articles in real time according to the GPS positioning signals;
The monitoring platform comprises: a data analysis module, a management portal;
The data analysis module is used for analyzing data from the monitoring terminal equipment and judging the current article transportation state in real time;
the management portal is used for displaying the article transportation state in real time and interacting with a user.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A method for monitoring the state of transportation of an article by using artificial intelligence, comprising the steps of:
S1, installing monitoring terminal equipment for each article in the article transportation process, and communicating with a monitoring platform in real time in a wireless communication mode;
s2, the installed monitoring terminal equipment collects information of transported objects based on the configuration of the internet of things sensor;
S3, monitoring the state of the transported object in real time according to the information data of the transported object collected in real time, and carrying out periodic reporting; when an abnormal condition occurs, the monitoring terminal equipment alarms and reports the abnormal state of the transported articles; the abnormal condition is judged based on a state vector algorithm, and specifically comprises the following steps:
s31, constructing an information data vector; the information data at least comprises position data, state data, vibration data and transport tool data of the transported articles; constructing information data vectors from the information data The method meets the following conditions:
Wherein a i1 to a in represent position data elements of the i-th transport item; b i1 to b im represent status data elements of the ith transport item; c i1 to c if represent vibration data elements of the ith transport item; d i1 to d ig denote transport data elements of the ith transport item, [ I ] denotes a transport item number space, [ J ] denotes an information data number space;
s32, classifying areas of the transported objects; from information data vectors In calling position data element to construct position data vectorThe method meets the following conditions:
position data vector for all transported items Clustering analysis is carried out, and the articles with the same type of analysis result are divided into articles in areas;
S33, judging the sports goods; the method specifically comprises the following steps:
S331, data vector for regional object Performing time derivation to obtain a time-varying vector/>, of the position data
S332, judging time-varying vector of position dataWhether the article is smaller than a preset first threshold value or not, if yes, judging that the article is a static article, and if not, judging that the article is an article in transportation;
S333, for the article in transport, time-varying vector of the position data thereof Performing cluster analysis, and judging the articles with the same analysis structure as articles with the same carrier;
s34, judging the transportation state; for co-carrier articles, from information data vectors In the process, the vibration data elements are called, and the vibration data vector/> isconstructedFor vibration data vectorPerforming cluster analysis to find out an outlier vibration data vector, and judging that the transported object is an abnormal vibration object;
S35, judging the state of the abnormal vibration article; the method comprises the steps of calling state data b i1,bi2,…,bim of an abnormal vibration article, constructing transportation state data { b i1,bi2,…,bim }, comparing the transportation state data with an expected state data interval set { [ b i1],[bi2],…,[bim ] } element by element, judging whether abnormal elements exist, judging that current transportation tool data are not abnormal if the abnormal elements exist, and judging that the current transportation tool data are abnormal if the abnormal transportation tool data are not abnormal;
s4, uploading the state of the transported object monitored in real time to a monitoring platform, processing the state based on the uploaded monitoring data by the monitoring platform, and generating an instruction based on user requirements by the monitoring platform to control the monitoring terminal equipment;
And S5, the monitoring platform transmits the processed data to the user side through the server and interacts with the user through the user side.
2. A method for monitoring the status of transportation of an item using artificial intelligence as claimed in claim 1, wherein: the method for communicating with the monitoring platform in real time in a wireless communication mode comprises the following steps:
S11, creating an interface at a monitoring terminal device end and a monitoring platform end;
S12, binding the IP address and the interface;
s13, realizing communication between the two interfaces through the appointed IP address.
3. A method for monitoring the status of transportation of an item using artificial intelligence as claimed in claim 1, wherein: the installed monitoring terminal equipment can collect information of transported objects based on the configuration of the internet of things sensor and comprises the following steps:
and (3) environmental data acquisition: data information acquisition is carried out on the temperature and humidity environment around the monitoring terminal;
And (3) geographic positioning data acquisition: carrying out coordinate positioning on geographic position information in the logistics transportation process to determine the position information of the article;
And (3) image shooting and acquisition: and after receiving a shooting instruction from the monitoring platform, collecting shooting image information of the state of the article in the logistics transportation process.
4. A method for monitoring the status of transportation of an item using artificial intelligence as claimed in claim 1, wherein: the real-time monitoring of the state of the transported object according to the information data of the transported object collected in real time further comprises the following steps:
s36, rechecking the article transportation state; the method specifically comprises the following steps:
S361, setting a D-S evidence theory;
s362, setting a D-S combination rule;
S363, calculating key parameter weights;
s364, setting corresponding thresholds according to the weights of the indexes and judging the article transportation state based on the D-S evidence theory.
5. The method for monitoring the transportation state of an article using artificial intelligence according to claim 4, wherein: the set D-S evidence theory:
Defining a basic probability distribution function:
Setting a quality function mapping m, namely 2 θ to 0, 1;
and m satisfies: When in use;
Then m is a probability distribution function of 2 θ;
Wherein, Is an empty set, m (A) is the confidence of A itself, θ is a certain finite set, 2 θ represents a set made up of all subsets of the expert ranking opinion table, A represents a set of assumptions in θ;
further, defining a confidence function Bel and a likelihood function Pl based on the probability distribution function;
Setting a mapping Bel 2 θ to 0, 1;
when meeting the requirements Bel(θ)＝1；
And for any subset a 1,A2,...,An of θ:
And has the following steps: When in use;
the map Pl.2 θ. Fwdarw.0, 1 is a belief function defined at θ;
wherein I represents the number of elements in set I;
setting a mapping Pl of 2 θ to 0, 1;
when meeting the requirements Pl(θ)＝1；
And for any subset a 1,A2,...,An of θ:
the map Pl.2 θ. Fwdarw.0, 1 is a belief function defined at θ;
Where I represents the number of elements in set I.
6. The method for monitoring the transportation state of an article using artificial intelligence according to claim 4, wherein: the set D-S combining rule:
Setting m 1,m2 to be the quality function defined on θ, respectively, then:
Wherein E, F are respectively the hypothesis sets in θ, A is not the null set; Is a normalization constant;
Setting m as a mass function synthesized by m 1,m2:
Setting a synthesis formula:
Wherein E i represents the i-th number in set E.
7. The method for monitoring the transportation state of an article using artificial intelligence according to claim 4, wherein: the calculating key parameter weights:
setting n indexes u j (j=1, 2,..n), and inviting k experts to rank the indexes;
the expert ranks the indexes according to the difference of the importance degrees of the indexes, wherein the most important index is 1, the least important index is n, and when the expert considers that a plurality of indexes are equally important, the indexes are ranked with the same serial number;
Recording the sequence of each index, and constructing a sequence opinion table;
acquiring all indexes collected by monitoring terminal equipment in the transportation process in real time, and calculating the weight of all indexes in an expert sorting opinion table based on the difference of transported articles and the expert sorting opinion table corresponding to different transported articles;
The collection index set u= { U 1,u2,...,un }, the rank array given by the ith expert is { a i1,ai2,...,ain }, and the membership functions of the rank transformation are determined for a typical rank as follows:
X(M)＝-p(M)lnp(M),M＝1,2,...,n
Wherein the method comprises the steps of
Let m=a ij, b ij＝X(aij),bij be the membership function value corresponding to the ranking number M; taking an average value of the array { b 1j,...,bkj }, marking as b j, and weighing 1-b j as the average recognition degree of k experts on the index u j;
The membership function value of k experts on the cognition of the index u is recorded as Q, and is defined as:
Qj＝max{b1j,b2j,...,bkj}
Setting the overall recognition degree of k experts on the index u j as x j;
xj＝(1-bj)(1-Qj)
and carrying out normalization treatment:
The weight vector α j for each index can be obtained.
8. The method for monitoring the transportation state of an article using artificial intelligence according to claim 4, wherein: setting corresponding thresholds according to the weights of the indexes, and judging the article transportation state based on the D-S evidence theory:
Setting the maximum boundary value of three key parameters with the maximum weight in the index as a system threshold, namely when any one of the three key parameters is acquired to reach a dangerous state range, waking up a monitoring system to start storing effective key data, and after the data within N seconds are acquired and stored, performing multi-data fusion processing on the acquired effective key parameters;
Performing basic trust distribution on N groups of effective key parameters acquired in N seconds through a set threshold value;
Normalization processing is carried out on the collected effective key parameters, and a basic trust distribution set theta= { safe, safer, more dangerous and dangerous } is set and identified, and a fused input matrix R is obtained according to D-S evidence:
based on the weights of the various indices, new evidence for each data is calculated:
Obtaining a final fusion result vector based on a synthesis formula:
Wherein a 1+A2+A3+A4 =1, when a 1 is the maximum value of four components in the fusion result vector, the transportation state is safe; when A 2 is the maximum value of the four components in the fusion result vector, the transportation state is safer; when A 3 is the maximum value of the four components in the fusion result vector, the transportation state is dangerous, and the transportation personnel can be reminded to slow down the speed; when A 4 is the maximum value of the four components in the fusion result vector, the transportation state is dangerous, and an alarm signal is generated at the moment to remind transportation personnel to stop and check immediately.
9. An artificial intelligence monitoring item transportation state system for implementing the method for monitoring item transportation state using artificial intelligence of any one of claims 1 to 8, comprising: monitoring terminal equipment and a monitoring platform;
The monitoring terminal device includes: the system comprises a humidity monitoring module, a temperature monitoring module, an image shooting module, an article transportation state collecting module, an alarm module, a wireless communication module and a GPS positioning module;
the humidity monitoring module is used for monitoring the humidity of the surrounding environment of the transported article in real time;
the temperature monitoring module is used for monitoring the temperature of the surrounding environment of the transported article in real time;
the image shooting module is used for shooting images of the transported objects in real time according to the instruction;
The article transportation state collection module is used for collecting state parameters in the article transportation process in real time;
the alarm module is used for receiving the state signal in the article transportation process in real time and carrying out alarm processing on the dangerous state signal in the article transportation process;
The wireless communication module is used for carrying out wireless communication with the monitoring platform and carrying out data transmission with the monitoring platform;
the GPS positioning module is used for updating positioning information in the process of transporting the articles in real time according to the GPS positioning signals;
The monitoring platform comprises: a data analysis module;
the data analysis module is used for analyzing data from the monitoring terminal equipment and judging the current article transportation state in real time.
10. The system for monitoring shipment status of items using artificial intelligence of claim 9, further comprising a management portal for displaying shipment status of items in real time and interacting with a user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410297060.8A CN117893121B (en) | 2024-03-15 | 2024-03-15 | System and method for monitoring article transportation state by utilizing artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410297060.8A CN117893121B (en) | 2024-03-15 | 2024-03-15 | System and method for monitoring article transportation state by utilizing artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117893121A CN117893121A (en) | 2024-04-16 |
| CN117893121B true CN117893121B (en) | 2024-06-07 |
Family
ID=90641525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410297060.8A Active CN117893121B (en) | 2024-03-15 | 2024-03-15 | System and method for monitoring article transportation state by utilizing artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117893121B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109426202A (en) * | 2017-09-01 | 2019-03-05 | 青岛大数华创科技有限公司 | A kind of multi-functional cargo transport monitoring system |
| CN110009251A (en) * | 2019-04-15 | 2019-07-12 | 西安邮电大学 | A method and system for dynamic adjustment and fusion of farmland multi-source information |
| CN110196566A (en) * | 2019-05-21 | 2019-09-03 | 安庆易达供应链管理有限公司 | A kind of transportational process monitoring system |
| CN112762991A (en) * | 2020-12-29 | 2021-05-07 | 北京无线电计量测试研究所 | Cargo transportation process state monitoring equipment and method |
| KR20210070524A (en) * | 2019-12-05 | 2021-06-15 | 주식회사 티허브 | Logistics Monitoring System and Method using a Smart Device |
| CN114971481A (en) * | 2022-06-07 | 2022-08-30 | 上海东普信息科技有限公司 | Logistics object transportation timeliness monitoring method, device, equipment and storage medium |
| CN115310675A (en) * | 2022-07-17 | 2022-11-08 | 云南电网有限责任公司信息中心 | Load estimation optimization method based on power grid user data set and neural network |
| CN115824298A (en) * | 2022-11-25 | 2023-03-21 | 中国农业银行股份有限公司 | Transportation detection method, device and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101652789A (en) * | 2007-02-12 | 2010-02-17 | 肖恩·奥沙利文 | Shared transportation system and service network |
| MX388130B (en) * | 2015-03-02 | 2025-03-19 | Locus Solutions Llc | SYSTEMS AND METHODS FOR MONITORING TRANSPORTED ITEMS. |
-
2024
- 2024-03-15 CN CN202410297060.8A patent/CN117893121B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109426202A (en) * | 2017-09-01 | 2019-03-05 | 青岛大数华创科技有限公司 | A kind of multi-functional cargo transport monitoring system |
| CN110009251A (en) * | 2019-04-15 | 2019-07-12 | 西安邮电大学 | A method and system for dynamic adjustment and fusion of farmland multi-source information |
| CN110196566A (en) * | 2019-05-21 | 2019-09-03 | 安庆易达供应链管理有限公司 | A kind of transportational process monitoring system |
| KR20210070524A (en) * | 2019-12-05 | 2021-06-15 | 주식회사 티허브 | Logistics Monitoring System and Method using a Smart Device |
| CN112762991A (en) * | 2020-12-29 | 2021-05-07 | 北京无线电计量测试研究所 | Cargo transportation process state monitoring equipment and method |
| CN114971481A (en) * | 2022-06-07 | 2022-08-30 | 上海东普信息科技有限公司 | Logistics object transportation timeliness monitoring method, device, equipment and storage medium |
| CN115310675A (en) * | 2022-07-17 | 2022-11-08 | 云南电网有限责任公司信息中心 | Load estimation optimization method based on power grid user data set and neural network |
| CN115824298A (en) * | 2022-11-25 | 2023-03-21 | 中国农业银行股份有限公司 | Transportation detection method, device and system |
Non-Patent Citations (2)
| Title |
|---|
| MISS: Multi-dimensional Information Sensing Surveillance for Cold Chain Logistics;Ding, H;《2013 IEEE 10TH INTERNATIONAL CONFERENCE ON MOBILE AD-HOC AND SENSOR SYSTEMS (MASS 2013)》;20140506;519-523 * |
| 一种基于传感器的快件物流过程检测方法及配套系统设计;丁奥;《物流技术》;20191025;第38卷(第10期);67-72 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117893121A (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119322941B (en) | Small unmanned aerial vehicle inspection data management method | |
| US11432469B2 (en) | Method for prediction of soil and/or plant condition | |
| US11325777B2 (en) | Systems and processes for space management of three dimensional containers including biological measurements | |
| CN119398645A (en) | Intelligent cargo tracking method, device, equipment and storage medium for transport agent | |
| CN114565162A (en) | Aircraft transportation state monitoring and safety protection method and system | |
| Liu et al. | Deep learning approach for sensor data prediction and sensor fault diagnosis in wind turbine blade | |
| Liu et al. | Validation of strain gauges for structural health monitoring with Bayesian belief networks | |
| CN119417353A (en) | A method and system for managing cargo loading information based on intelligent shelves | |
| CN118133679A (en) | PHM method based on digital twin unmanned aerial vehicle inertial navigation | |
| CN112985494A (en) | Cold chain wisdom logistics transportation on-line real-time supervision cloud platform based on big data and artificial intelligence | |
| CN119692792A (en) | Agricultural product circulation traceability method and system | |
| CN117893121B (en) | System and method for monitoring article transportation state by utilizing artificial intelligence | |
| CN117953398A (en) | Intelligent water area condition monitoring method and system based on unmanned plane river patrol technology | |
| CN120370371A (en) | GPS-RFID dual-mode tracking and positioning method and system for postal bags | |
| CN119151136B (en) | Farm and pasture composite area grass and livestock balance assessment analysis method and system | |
| CN120450574A (en) | An intelligent unmanned warehouse scheduling system for spare parts | |
| EP4252184A1 (en) | Artificial intelligence camera for visual inspection with neural network training onboard | |
| CN119712455A (en) | A wind turbine blade infrared monitoring system and method based on drone inspection | |
| CN119918015A (en) | Dynamic monitoring and management platform based on vision and sensor fusion | |
| EP3413153A1 (en) | Method and distributed control system for carrying out an automated industrial process | |
| CN116049638A (en) | A transformer vibration detection method, system, device and storage medium | |
| EP4141596A1 (en) | Method of transmitting process data to a machine learning application | |
| Zhang et al. | Self-Starting Monitoring and Dynamic Sampling of High-Dimensional Data Streams | |
| CN120763849B (en) | Soil state monitoring method and system based on sensor network | |
| CN118915848B (en) | A precise control method and system for cold chain equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240715 Address after: Room 501, 5th Floor, Main Building, Hefei Lianxin Power Supply Co., Ltd., No. 61 Yulan Avenue, High tech Zone, Hefei City, Anhui Province, 230000 Patentee after: Anhui Suiren Networking Technology Co.,Ltd. Country or region after: China Address before: 230000 room 303-1148, Nangang Science Park, the intersection of Dabieshan road and Tianlong Road, high tech Zone, Hefei City, Anhui Province Patentee before: Anhui zhixiangyun Technology Co.,Ltd. Country or region before: China Patentee before: Anhui Suiren Networking Technology Co.,Ltd. |